Humans can be tracked with unique 'fingerprint' based on how their bodies block Wi-Fi signals
Technology
141
Beiträge
102
Kommentatoren
30
Aufrufe
-
The Sapienza computer scientists say Wi-Fi signals offer superior surveillance potential compared to cameras because they're not affected by light conditions, can penetrate walls and other obstacles, and they're more privacy-preserving than visual images.
[…] The Rome-based researchers who proposed WhoFi claim their technique makes accurate matches on the public NTU-Fi dataset up to 95.5 percent of the time when the deep neural network uses the transformer encoding architecture.
Can I become obese in a day to avoid being fingerprinted?
-
Microwave based ground penetrating radar is actually different from WiFi. Also the technology referenced in the link is a motion based body locator, not an identity recognition device.
This is different technology doing different things than what the original article was talking about.
-
Can I become obese in a day to avoid being fingerprinted?
I did that over 40 years.
Doesn’t help. -
You are correct because something similar has already been used
Microwaves are the same as wifi waves, these are able to detect bodies and whether the bodies are beating or not
WiFi uses a subset of the significantly wider microwave band. Ground Penetrating Radar also uses a subset of the microwave band. While there can be some overlap, the frequencies desired for GPR will very broadly based on what you are looking for, what you are looking in, and how deep you are looking for that thing. The wattage supplied can also differ.
WiFi and Microwaves in general are most definitely not the same thing and I will absolutely encourage you to not set up a 1kW 3GHz jamming antenna for your WiFi needs.
Could you use WiFi for search and rescue? Maybe for a narrow set of circumstances, but in almost all situations a dedicated GPR option will be better.
This also won't identify a victim, only revealing that one exists.
-
The Sapienza computer scientists say Wi-Fi signals offer superior surveillance potential compared to cameras because they're not affected by light conditions, can penetrate walls and other obstacles, and they're more privacy-preserving than visual images.
[…] The Rome-based researchers who proposed WhoFi claim their technique makes accurate matches on the public NTU-Fi dataset up to 95.5 percent of the time when the deep neural network uses the transformer encoding architecture.
Well of course the Sapienza scientists would figure this out, Agent 47 keeps killing everyone in the labs
-
Yeah, like, why learn how to split the atom if all we can do is splode stuff. It's not like we can cure cancer or power things without emitting planet killing gasses or anything.
But, but, splosion make line go up. Splosion good...?
-
The Sapienza computer scientists say Wi-Fi signals offer superior surveillance potential compared to cameras because they're not affected by light conditions, can penetrate walls and other obstacles, and they're more privacy-preserving than visual images.
[…] The Rome-based researchers who proposed WhoFi claim their technique makes accurate matches on the public NTU-Fi dataset up to 95.5 percent of the time when the deep neural network uses the transformer encoding architecture.
Time to start making faraday clothes.
-
Time to start making faraday clothes.
With wild and crazy shape lines. Ultra futuristic fashion here we come!
-
The Sapienza computer scientists say Wi-Fi signals offer superior surveillance potential compared to cameras because they're not affected by light conditions, can penetrate walls and other obstacles, and they're more privacy-preserving than visual images.
[…] The Rome-based researchers who proposed WhoFi claim their technique makes accurate matches on the public NTU-Fi dataset up to 95.5 percent of the time when the deep neural network uses the transformer encoding architecture.
Time to carry a WiFi jammer
-
95.5% accuracy is abysmal for any use case these people want to use it for
It's not at all bad for an initial proof of concept.
